English
Related papers

Related papers: APEX: Learning Adaptive Priorities for Multi-Objec…

200 papers

Large-scale general domain pretraining followed by downstream-specific finetuning has become a predominant paradigm in machine learning. However, discrepancies between the pretraining and target domains can still lead to performance…

Machine Learning · Computer Science 2024-10-15 Ruiyi Zhang , Sai Ashish Somayajula , Pengtao Xie

Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflicting objectives, where naive aggregation of preferences can…

Computation and Language · Computer Science 2026-05-26 Peter Chen , Xiaopeng Li , Xi Chen , Tianyi Lin

Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires jointly maximizing both exploration and skill diversity.…

Machine Learning · Computer Science 2026-03-17 Geonwoo Cho , Jaemoon Lee , Jaegyun Im , Subi Lee , Jihwan Lee , Sundong Kim

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Dexterous manipulation tasks usually have multiple objectives, and the priorities of these objectives may vary at different phases of a manipulation task. Varying priority makes a robot hardly or even failed to learn an optimal policy with…

Robotics · Computer Science 2023-09-15 Lingfeng Tao , Jiucai Zhang , Xiaoli Zhang

The push for efficient text to image synthesis has moved the field toward one step sampling, yet existing methods still face a three way tradeoff among fidelity, inference speed, and training efficiency. Approaches that rely on external…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Deyuan Liu , Peng Sun , Yansen Han , Zhenglin Cheng , Chuyan Chen , Tao Lin

We propose an Adagrad-like algorithm for multi-objective unconstrained optimization that relies on the computation of a common descent direction only. Unlike classical local algorithms for multi-objective optimization, our approach does not…

Optimization and Control · Mathematics 2026-02-06 Marianna De Santis , Gabriele Eichfelder , Margherita Porcelli

Recent advancements in artificial intelligence, particularly deep neural networks, have pushed the boundaries of what is achievable in complex tasks. Traditional methods for training neural networks in classification problems often rely on…

Machine Learning · Computer Science 2024-09-10 Jaouad Dabounou

Adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models to the downstream tasks. However, after reviewing existing adapters, we find they generally fail to fully…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Yumiao Zhao , Bo Jiang , Xiao Wang , Qin Xu , Jin Tang

Additive parameter updates, as used in gradient descent and its adaptive extensions, underpin most modern machine-learning optimization. Yet, such additive schemes often demand numerous iterations and intricate learning-rate schedules to…

Machine Learning · Computer Science 2026-03-25 Han Kim , Hyungjoon Soh , Vipul Periwal , Junghyo Jo

We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$…

Machine Learning · Computer Science 2026-02-24 Zhenshuo Zhang , Minxuan Duan , Youran Ye , Hongyang R. Zhang

Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static preference weight…

Machine Learning · Computer Science 2026-04-28 Wenzhe Xu , Biao Liu , Yiyang Sun , Xin Geng , Ning Xu

Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating individual factors, we observe that, in practice, such…

Machine Learning · Computer Science 2026-02-24 Guoxia Wang , Shuai Li , Congliang Chen , Jinle Zeng , Jiabin Yang , Dianhai Yu , Yanjun Ma , Li Shen

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…

Artificial Intelligence · Computer Science 2026-05-26 Erhan Zhang , Yiqun Chen , Zechun Niu , Wei Yang , Xiaochi Wei , Yan Gao , Yi Wu , Yao Hu , Jiaxin Mao

Recent years have witnessed remarkable progress in 3D content generation. However, corresponding evaluation methods struggle to keep pace. Automatic approaches have proven challenging to align with human preferences, and the mixed…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Weitao Wang , Haoran Xu , Yuxiao Yang , Zhifang Liu , Jun Meng , Haoqian Wang

Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code generation. We formalize this setting using a…

Machine Learning · Computer Science 2026-05-19 Shaddin Dughmi , Mahdi Haghifam , Yusuf Hakan Kalayci

Multi-Task Learning is a learning paradigm that uses correlated tasks to improve performance generalization. A common way to learn multiple tasks is through the hard parameter sharing approach, in which a single architecture is used to…

Machine Learning · Computer Science 2022-04-15 Angelica Tiemi Mizuno Nakamura , Denis Fernando Wolf , Valdir Grassi

Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that blurs generation, critique, and revision, making credit…

Artificial Intelligence · Computer Science 2026-03-24 Zhongyi Li , Wan Tian , Jingyu Chen , Kangyao Huang , Huiming Zhang , Hui Yang , Tao Ren , Jinyang Jiang , Yijie Peng , Yikun Ban , Fuzhen Zhuang

Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack fine-grained expressiveness or introduce token-level alignment with…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Junyi Hu , Tian Bai , Fengyi Wu , Wenyan Li , Zhenming Peng , Yi Zhang

Most automated peer review systems rely on textual manuscript content alone, leaving visual elements such as figures and external scholarly signals underutilized. We introduce REM-CTX, a reinforcement-learning system that incorporates…

Computation and Language · Computer Science 2026-04-02 Pawin Taechoyotin , Daniel E. Acuna